Rochester Institute of Technology
Optimizing Neural Networks for IIoT Attack Detection
Abstract
dc:description.abstractThe Industrial Internet of Things (IIoT) stands as a revolutionary force, intertwining physical devices, sensors, and industrial systems to usher in advanced automation and data-driven decision-making across various sectors. However, this increased connectivity has exposed these systems to a growing array of cyber threats. Safeguarding IIoT environments becomes crucial to maintain the integrity, availability, and confidentiality of critical industrial processes. In response, this research explores the optimization of neural network parameters using Genetic Algorithms (GA). The application of GA has led to achieve a remarkable accuracy of 95% across various attack types. The results demonstrate a high performance in identifying complex attack patterns, contributing to the resilience of IIoT systems against emerging cyber threats.
Degree
thesis:*- Name thesis:degree_name
- Cybersecurity (MS)
- Level thesis:degree_level
- Thesis
- Discipline thesis:degree_discipline
- Cybersecurity, Department of
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Alblooshi, Hamad
- Contributors dc:contributor
-
- Kevser Ovaz Akpinar
Subjects
dc:subject × 1Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.rit.edu/theses/11923